Research Article

Application of Cox Proportional Hazards Model in Case of Tuberculosis Patients in Selected Addis Ababa Health Centres, Ethiopia

Table 9

The six highest differences in the parameter estimates of the variables included in the model in Table 7 when the data value for each patient is in turn deleted from the model, approximate delta-betas for age ( ), TBC ( ), HIV ( ), and age by HIV ( ).
(a)

Deleted Obs. ( ) % change parameter of the std. errorDeleted Obs. ( ) % change parameter of the std. error

7300.002323430.57413−0.043998718.94
162−0.002120527.90585−0.042843518.44
262−0.002095727.58343−0.042759918.41
421−0.001762423.20368−0.042347318.23
5420.001700222.37544−0.0421418.14
5800.00161121.20447−0.04160117.91
Sd. error ( ) of full model = 0.00760Sd. error ( ) of full model = 0.23231

(b)

Deleted Obs. ( ) % change parameter of the std. errorDeleted Obs. ( ) % change parameter of the std. error

1330.118548423.615480.004206831.07
548−0.115590823.02630.003274524.18
2040.114646422.83133−0.003166223.38
244−0.105600321.03204−0.003029822.38
162−0.100892120.10244−0.002700119.94
262−0.09844319.60282−0.002487318.37
Sd. error ( ) of full model = 0.50215Sd. error ( ) of full model = 0.01354